How to Use the ChartHop MCP in OpenAI Agents SDK

Q: How do I connect ChartHop to the OpenAI Agents SDK?

Install the openai-agents package. Create an MCPServerStreamableHttp instance with your Vinkius URL and pass it to your Agent constructor in the mcpservers list.

Q: Can the OpenAI Agents SDK read ChartHop compensation data?

Yes, if your token has permissions. The agent uses listplanningscenarios to read headcount and compensation planning data. Guardrails can block this if you want to restrict access.

Q: Does the OpenAI Agents SDK auto-discover ChartHop tools?

It does. Once connected, tools like getorganizationsummary populate automatically. Set cacheToolsList=True to speed up initialization.

Connect ChartHop to the OpenAI Agents SDK to build production-ready HR assistants that query headcount and org data with strict guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ChartHop MCP to OpenAI Agents SDK

Create your Vinkius account to connect ChartHop to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup ChartHop with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run ChartHop planning scenarios with OpenAI Agents SDK

Production HR systems require exact data, not guesses. By connecting this MCP Server, your agent pulls actual compensation models using `list_planning_scenarios`. You get immediate access to active workforce projections without writing custom API polling logic. Handoffs between specialized agents become trivial. One agent calculates budget constraints while another fetches specific roles via `list_organization_jobs`. The built-in guardrails validate every read request before execution, preventing accidental data dumps.

Query individual employee records

When managers ask about direct reports, your agent needs exact context. The `get_person_details` tool grabs specific profile information, from tenure to reporting lines. You avoid hallucinated job histories entirely. Full tracing in the OpenAI dashboard means you see exactly when the agent calls `get_job_details`. If a user asks about a specific engineering role, you can audit the exact payload the model received to generate its answer.

Map complex team structures

Company directories rarely fit into standard context windows neatly. Using `list_organization_departments` and `list_organization_teams`, the agent navigates the hierarchy dynamically. It only pulls the branches it needs to answer the user's question. Setup takes minutes with `MCPServerStreamableHttp`. You pass the URL, set `cacheToolsList=True` for performance, and the tools auto-discover. Your production system stays fast while querying live org data over the MCP protocol.

Setup guide

Set up ChartHop MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all ChartHop tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives ChartHop tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate ChartHop tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="ChartHop Agent",
            instructions="You have access to ChartHop tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by ChartHop. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect ChartHop now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about ChartHop MCP in OpenAI Agents SDK

Install the `openai-agents` package. Create an `MCPServerStreamableHttp` instance with your Vinkius URL and pass it to your Agent constructor in the `mcp_servers` list.

Yes, if your token has permissions. The agent uses `list_planning_scenarios` to read headcount and compensation planning data. Guardrails can block this if you want to restrict access.

It does. Once connected, tools like `get_organization_summary` populate automatically. Set `cacheToolsList=True` to speed up initialization.

You control the execution constraints. The SDK lets you enforce guardrails before `list_organization_people` runs, capping the amount of data pulled in a single turn.

Your agent accesses sensitive salary and reporting lines through an ephemeral V8 Isolate Sandbox. Vinkius destroys the environment immediately after the `get_person_details` call finishes. No persistent storage touches your HR records.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript